checkpoint

type CRIUDumpManifest struct {
	CRIU     CRIUSettings                 `yaml:"criu"`
	ExtMnt   []ExternalMountManifestEntry `yaml:"extMnt,omitempty"`
	External []string                     `yaml:"external,omitempty"`
	SkipMnt  []string                     `yaml:"skipMnt,omitempty"`
}

type CRIUSettings struct {

	// GhostLimit is the maximum ghost file size in bytes.
	// Ghost files are deleted-but-open files that CRIU needs to checkpoint.
	// 512MB is recommended for GPU workloads with large memory allocations.
	GhostLimit uint32 `yaml:"ghostLimit"`

	// Timeout is the CRIU operation timeout in seconds.
	// 6 hours (21600s) is recommended for large GPU model checkpoints.
	Timeout uint32 `yaml:"timeout"`

	// LogLevel is the CRIU logging verbosity (0-4).
	LogLevel int32 `yaml:"logLevel"`

	// WorkDir is the CRIU work directory for temporary files.
	WorkDir string `yaml:"workDir"`

	// AutoDedup enables auto-deduplication of memory pages.
	AutoDedup bool `yaml:"autoDedup"`

	// LazyPages enables lazy page migration (experimental).
	LazyPages bool `yaml:"lazyPages"`

	// LeaveRunning keeps the process running after checkpoint (dump only).
	LeaveRunning bool `yaml:"leaveRunning"`

	// ShellJob allows checkpointing session leaders (containers are often session leaders).
	ShellJob bool `yaml:"shellJob"`

	// TcpClose closes TCP connections instead of preserving them (pod IPs change on restore).
	TcpClose bool `yaml:"tcpClose"`

	// FileLocks allows checkpointing processes with file locks.
	FileLocks bool `yaml:"fileLocks"`

	// OrphanPtsMaster allows checkpointing containers with TTYs.
	OrphanPtsMaster bool `yaml:"orphanPtsMaster"`

	// ExtUnixSk allows external Unix sockets.
	ExtUnixSk bool `yaml:"extUnixSk"`

	// LinkRemap handles deleted-but-open files.
	LinkRemap bool `yaml:"linkRemap"`

	// ExtMasters allows external bind mount masters.
	ExtMasters bool `yaml:"extMasters"`

	// ManageCgroupsMode controls cgroup handling: "ignore" lets K8s manage cgroups.
	ManageCgroupsMode string `yaml:"manageCgroupsMode"`

	// LibDir is the path to CRIU plugin directory (e.g., /usr/local/lib/criu).
	// Required for CUDA checkpoint/restore.
	LibDir string `yaml:"libDir"`

	// AllowUprobes allows user-space probes (required for CUDA checkpoints).
	AllowUprobes bool `yaml:"allowUprobes"`

	// SkipInFlight skips in-flight TCP connections during checkpoint/restore.
	SkipInFlight bool `yaml:"skipInFlight"`
}

type CheckpointManifest struct {
	CheckpointID string    `yaml:"checkpointId"`
	CreatedAt    time.Time `yaml:"createdAt"`

	CRIUDump   CRIUDumpManifest         `yaml:"criuDump"`
	K8s        SourcePodManifest        `yaml:"k8s"`
	Filesystem FilesystemManifest       `yaml:"filesystem"`
	Namespaces []NamespaceManifestEntry `yaml:"namespaces"`
}

type CheckpointOutcome struct {
	CheckpointID  string
	CheckpointDir string
	Data          *CheckpointManifest
}

type CheckpointRequest struct {
	ContainerID   string
	ContainerName string // K8s container name (for K8s API volume type lookup)
	CheckpointID  string
	CheckpointDir string
	NodeName      string
	PodName       string
	PodNamespace  string
}

type CheckpointSpec struct {
	// BasePath is the base directory for checkpoint storage (PVC mount point).
	BasePath string `yaml:"basePath"`

	// CRIU options for dump operations
	CRIU CRIUSettings `yaml:"criu"`

	// RootfsExclusions defines paths to exclude from rootfs diff capture
	RootfsExclusions FilesystemConfig `yaml:"rootfsExclusions"`
}

type Checkpointer struct {
	// contains filtered or unexported fields
}

type ConfigError struct {
	Field   string
	Message string
}

type ContainerInfoSnapshot struct {
	PID        int
	RootFS     string
	UpperDir   string
	OCISpec    *specs.Spec
	MountInfo  []MountInfo
	Namespaces map[NamespaceType]*NamespaceInfo
}

type DiscoveryClient struct {
	// contains filtered or unexported fields
}

type ExternalMountManifestEntry struct {
	Key string `yaml:"key"`
	Val string `yaml:"val"`
}

type FilesystemConfig struct {
	// SystemDirs are system directories that should be excluded from rootfs diff.
	// These directories are typically injected/bind-mounted by NVIDIA GPU Operator
	// at container start time, so they already exist in the restore target.
	// Excluding them prevents conflicts (especially socket files which cannot be overwritten).
	// Default: ["./usr", "./etc", "./opt", "./var", "./run"]
	SystemDirs []string `yaml:"systemDirs"`

	// CacheDirs are cache directories that can safely be excluded to reduce checkpoint size.
	// Model weights and other cached data are typically re-downloaded if needed.
	// Default: ["./.cache/huggingface", "./.cache/torch"]
	CacheDirs []string `yaml:"cacheDirs"`

	// AdditionalExclusions are custom paths to exclude from the rootfs diff.
	// Use this for application-specific exclusions.
	// Paths should be relative with "./" prefix (e.g., "./data/temp").
	AdditionalExclusions []string `yaml:"additionalExclusions"`
}

type FilesystemManifest struct {
	Exclusions      FilesystemConfig `yaml:"exclusions"`
	UpperDir        string           `yaml:"upperDir,omitempty"`
	ExternalPaths   []string         `yaml:"externalPaths,omitempty"`
	BindMountDests  []string         `yaml:"bindMountDests,omitempty"`
	HasRootfsDiff   bool             `yaml:"hasRootfsDiff"`
	HasDeletedFiles bool             `yaml:"hasDeletedFiles"`
}

type MountInfo struct {
	MountID      string
	ParentID     string
	MountPoint   string
	Root         string
	FSType       string
	Source       string
	Options      string
	SuperOptions string
}

type MountPolicy struct {
	Externalized []string
	Skipped      []string
}

type NamespaceInfo struct {
	Type       NamespaceType
	Inode      uint64
	IsExternal bool // Whether NS is external (shared with pause container)
}

type NamespaceManifestEntry struct {
	Type       string `yaml:"type"`       // net, pid, mnt, etc.
	Inode      uint64 `yaml:"inode"`      // Namespace inode
	IsExternal bool   `yaml:"isExternal"` // Whether namespace is external (shared)
}

type NamespaceType string

type SourcePodManifest struct {
	ContainerID  string `yaml:"containerId"`
	PID          int    `yaml:"pid"`
	SourceNode   string `yaml:"sourceNode"`
	PodName      string `yaml:"podName"`
	PodNamespace string `yaml:"podNamespace"`
}